Syllabus for ISM-643: Analysis and Design of Intelligent Agents and Systems

Instructor: Dr. Liping Liu, CBA360, X5947

Credits: 3 hours

Applicable Term: Spring 2026 (January 15-May 15)

Textbook:

• Main Text: Liping Liu, Requirements Modeling and Coding, World Scientific Publishing, 2020 (ISBN: 978-1-78634-882-1)
• Lecture Notes 1-5: Supplementary Reading on Generative AI Applications Development (provided online at ecourse.org).

Reference Resources:

• Book: Matt Weisfeld, The Object-Oriented Thought Process, 4th/2013,  ISBN: 9780321861276, Addison-Wesley Professional 
• Book: Frederick P. Brooks Jr., Mythical Man Moon: Essays on Software Engineering, Addison Wesley, 1995. ISBN-13: 858-0001065793. (Note: the methodology is outdated, but the book is a timeless piece on experience of managing complex projects.)
• Book: Rebecca Wirfs-Brock, Alan McKean, Object Design: Roles, Responsibilities, and Collaborations, Addison-Wesley Professional (November 18, 2002), ISBN-13: 978-0201379433. (Note: Written by a OO pioneer, the book offers many practical strategies and techniques such as CRC)

Learning C# for Prerequisite:

1. Short Free Videos on Basic Visual C# Programming at eduonix.com: https://www.eduonix.com/courses/Software-Development/Learn-C-Sharp-Programming-From-Scratch (Recommended Use: watch the videos and follow the hands-on exercises along the videos)
2. Short Tutorials on Visual C# Programming with Quiz Questions at TutorialsTeacher.com: https://www.tutorialsteacher.com/csharp (Recommended Use: take quizzes and tests to check your skills and understandings)

Office Hours: 

• 12:30-2:00 PM on Tuesdays and Thursdays (Instructor)

Course Description: Analysis and Design of Intelligent Agents and Systems introduces students to modern approaches for analyzing, modeling, and designing business information systems, while integrating hands-on development of Generative AI applications and intelligent agents. Students learn core systems analysis and design techniques including object-oriented principles, business process modeling, business object modeling, use case modeling, storyboarding, and user interface design. In parallel, students develop GenAI-enabled applications using Langflow, exploring large language models (LLMs), prompt engineering and prompt templates, tokenization and embeddings, retrieval-augmented generation (RAG), vector databases (e.g., ChromaDB), and agent-style workflows for planning and decision-making. Through guided projects such as a language translator, chatbot, help desk assistant, and travel agent, students gain practical experience designing intelligent solutions that address real organizational needs.

Future Catalog Description: This course covers systems analysis and design of traditional transactional systems and modern generative AI applications and agents. Students learn modeling techniques (business process, software architecture, and use cases) and build practical AI-powered applications using prompt engineering, embeddings, retrieval-augmented generation (RAG), vector databases, and agents. Prerequisite: 6500:602 or 6200:603

Objectives: By the end of this course, students will be able to:

1. Understand the role of systems analysts in business and the process of systems development

2. Analyze business problems and requirements and translate them into clear functional and non-functional system specifications.

3. Model and design information systems using unified modeling language (UML) and computer-aided software engineering (CASE) tools for business process modeling, software architecture modeling, and use case modeling.

4. Develop Generative AI applications, including LLM-based workflows such as translators and chatbots.

5. Implement retrieval-augmented generation (RAG) solutions using chunking, embeddings, and vector databases (e.g., ChromaDB) to support knowledge-grounded responses.

6. Design intelligent agent workflows that incorporate planning and decision logic (loops and branching) and demonstrate how agent-based systems can support real organizational use cases.

Weekly Schedule:

• Week 1: Introduction: information systems, systems analysis, and systems development life cycle (Chapter 1)
• Week 2: Generative AI Application Development 1: Large Language Models, GenAI Application Development, Langflow, and Language Translator Development (supplementary reading)
• Week 3: Generative AI Application Development 2: Prompt Engineering, Prompt Template for dynamic prompts, and Chatbot Development (supplementary reading)
• Week 4: Generative AI Application Development 3: Machine Learning, Tokenization, Word Embedding, Query ChatGPT using Python, Generate Word Embedding using Python, Chef-Dietitian Duo Development (supplementary reading) 
• Week 5: Generative AI Application Development 4: Retrieval Augmented Generation, Chunking and Embedding, Vector Database (chroma DB), Restaurant Help Desk System Development (supplementary reading)
• Week 6: Generative AI Application Development: Action planning using loops and decisions, Model Context Protocol (MCP), Travel Agent Development
• Week 7: Midterm Exam
• Week 8: Object-Oriented Programming Principles (Chapter 2)
• Week 9: Modeling Business Processes: Data Flow Diagrams <=> Operations and Activity Diagrams <=> Methods (Chapter 3)
• Week 10: Modeling Business Processes: Nested Loops in Activity Diagrams, Advanced Functions and Function Invocations (Chapter 4)
• Week 11: Modeling Business Objects: Concepts of Object-Orientation. (Chapter 5)  
• Week 12: Modeling Business Objects: Class Diagramming (Chapter 6)
• Week 13: Modeling User Behavior: Use Case Modeling, Optimization, and Storyboarding (Chapter 9)
• Week 14: Modeling user Behavior: Use Case Storyboarding and Interface Design, User Interface Design Principles (Chapters 10 and 11)
• Week 15: Final Exam

Additional Topics:

• Modeling and Programming Business Objects III: Advanced Object Modeling (Chapter 7) 
• Collaboration Modeling (Chapter 15)
• Collaboration Programming (Chapter 14)

Exam Schedule: This course will have two major exams scheduled (see the weekly schedule above). The exam includes both hands-on and written questions

Assignments: Homework is assigned once a week. Assignments are due at the beginning of each class. No late homework will be graded. Please show your work in a neat and orderly fashion. Write or type your work on one side and in every other line. For electronic submissions, it is the student's responsibility to submit correct files in correct formats. 

Attendance: Attendance is MUST and will be 10% of your final grade. Attendance will be managed by ecourse.org system. The formula for computing your attendance grade is non-linear. It will take 3 points off for the first absence and 7 points off for second absence. If you missed the equivalent of three-week classes, you fail the course automatically. Under special situations, you can take a class online with the following guidelines:

1. You must obtain permission from the instructor at least one day ahead of the online session
2. Follow the lecture or its recordings to perform all in-class hands-on exercises and take notes. Within one day of the class, submit your notes and the finished exercises to ecourse.org as Proof of Attendance for the online session. 
3. All weekly assignments are due at the same time as in-person classes. All exams must be onsite.

Quizzes: Quizzes are used regularly to check your completion or preparation of assignments.

Makeup: Each student with appropriate excuses may have at most one chance to makeup homework or quiz. Note that it is your privilege but not right to have this special favor. Also, all makeups must be completed within one week of due date and before answer key is released. 

Grades: Your final grades will be calculated by the following formulas:

40% (HW) + 50% (Tests)  + 10% (Attendance)

A = 93-100%; A– = 90-92%; B+ = 87-89%; B = 83-86%; B– = 80-82%; C+ = 77-79%; C = 73-76%; C– =70-72%; D = 60-69%; F = 59% and less

Misconduct: Academic misconduct by a student shall include, but not limited to: disruption of classes, giving and receiving unauthorized aid on exams or in the preparation of assignments, unauthorized removal of materials from the library, or knowingly misrepresenting the source of any academic work. Academic misconduct by an instructor shall include, but not limited to: grading student work by criteria other than academic performance or repeated and willful neglect in the discharge of duly assigned academic duties.

On Collaboration: All for-credit assignments, except for those designated as group projects, must be done independently, and collaboration in providing or asking for answers to those assignments constitutes cheating. 

On AI Tools: In this class, I allow students to use AI tools to help their learning. However, submitting AI generated work for credits is a violation of academic code. If a submitted work is suspected to be AI generated, the student will be asked to reproduce the submitted work in front of the instructor. 

School Rule Cited: For graduate students that have been caught cheating:   First offense = either a zero on the exam or assignment, or an F in the course; Second offense = Either an F in the course or expulsion (depending upon the punishment of the first offense)